Conference paper Open Access

Flow R-CNN: Flow-Enhanced Object Detection

Psaltis, Athanasios; Dimou, Anastasios; Alvarez, Federico; Daras, Petros


MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nam##2200000uu#4500</leader>
  <datafield tag="942" ind1=" " ind2=" ">
    <subfield code="a">2021-09-01</subfield>
  </datafield>
  <controlfield tag="005">20210901014823.0</controlfield>
  <controlfield tag="001">4603216</controlfield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">CERTH</subfield>
    <subfield code="a">Dimou, Anastasios</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="a">Alvarez, Federico</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">CERTH</subfield>
    <subfield code="a">Daras, Petros</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">3168828</subfield>
    <subfield code="z">md5:45b389219150c398b14d3866eecc6b93</subfield>
    <subfield code="u">https://zenodo.org/record/4603216/files/ICPR2020__CADL_.pdf</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2021-02-21</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire</subfield>
    <subfield code="p">user-787061</subfield>
    <subfield code="o">oai:zenodo.org:4603216</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">CERTH</subfield>
    <subfield code="a">Psaltis, Athanasios</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Flow R-CNN: Flow-Enhanced Object Detection</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-787061</subfield>
  </datafield>
  <datafield tag="536" ind1=" " ind2=" ">
    <subfield code="c">787061</subfield>
    <subfield code="a">Advanced tools for fighting oNline Illegal TrAfficking</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">https://creativecommons.org/licenses/by/4.0/legalcode</subfield>
    <subfield code="a">Creative Commons Attribution 4.0 International</subfield>
  </datafield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="a">cc-by</subfield>
    <subfield code="2">opendefinition.org</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">&lt;p&gt;This work addresses the problem of multi-task object detection in an efficient, generic but at the same time simple way, following the recent and highly promising studies in the computer vision field, and more specifically the Region-based Convolutional Neural Network (R-CNN) approach. A flow-enhanced methodology for object detection is proposed, by adding a new branch to predict an object-level flow field. Following a scheme grounded on neuroscience, a pseudo-temporal motion stream is integrated in parallel to the classification, bounding box regression and segmentation mask prediction branches of Mask R-CNN. Extensive experiments and thorough comparative evaluation provide a detailed analysis of the problem at hand and demonstrate the added value of the involved object-level flow branch. The overall proposed approach achieves improved performance in the six currently broadest and most challenging publicly available semantic urban scene understanding datasets, surpassing the region-based baseline method.&lt;/p&gt;</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.1007/978-3-030-68763-2_52</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">conferencepaper</subfield>
  </datafield>
</record>
23
19
views
downloads
Views 23
Downloads 19
Data volume 60.2 MB
Unique views 21
Unique downloads 17

Share

Cite as